The revolution in cancer treatments has one major roadblock: computing. Why? With 23.6 million new cases of cancer expected worldwide by 2030, pathology samples available for medical research grow by the day. Now, when these samples are gene-sequenced and matched with gene-specific data on successful cancer treatments, researchers can produce powerful recommendations for the most effective treatments for individual patients. Armed with the data and recommendations, oncologist will stand ready to offer targeted therapies representing a higher likelihood of successful results. But standing in the way is the need to find more efficient and cost-effective methods to sequence the human genome, which represents the process of sorting and analyzing the unique “alphabet soup” of each individual’s DNA.
Presently computing is in the way of this revolutionary near-term future. As reported in University of Virginia News by Elizabeth Thiel Mather, the limits on the speed for not only moving but also processing data are frustrating. To sequence a single human pathology sample, as well as analyze it against other DNA samples can take 20 hours. A course of cancer treatment entails many samples, hence the 20 hours per sample accumulates really fast. University of Virginia (UVA) reports that to sequence and analyze the pathology samples from the worldwide cases expected by 2030, researchers would demand storage equivalent to 3 million of today’s highest-capacity computer drives combined with proportional computational horsepower. But an answer may be on the horizon.
Center for Research in Intelligent Storage and Processing Memory (CRISP)
The University of Virginia is leading this 11-university consortium called CRISP. University of Virginia was selected to lead the charge for this $27.5 million initiative in early 2018 to remove the “memory wall.” Led by University of Virginia engineers, center investigators are designing a new architecture combining processing and memory into one unit. And as they are maintaining and housing the data at or adjacent to the processor, the mount of data and associated speed at which it is processed can be significantly increased, reports Ms. Thiel Mather of University of Virginia News.
Part of a $200 million, five-year national program, CRISP funds centers led by six top research universities including UVA, University of California at Santa Barbara, Carnegie Mellon University, Purdue University, the University of Michigan and The University of Notre Dame. The Joint University Microelectronics Program is managed by North Carolina-based Semiconductor Research Corporation, a consortium that involves engineers, and scientists from technology companies, universities and government agencies.
The CRISP grand challenge is to significantly lower the effort barrier for every day programmers to achieve highly portable, “bare-metal,” and understandable performance across a wide range of heterogeneous, IMS architectures. This will democratize high-performance, heterogeneous, data-intensive computing, to enhance productivity of the IT workforce and enable an improved software ecosystem that opens new markets for computer systems. The Research Team is led by Director Kevin Skadron. Sponsors include many name brand government technology contractors as well as DARPA.